High-performance computing-oriented method for automatically deploying execution environment along with job

Abstract

A high-performance computing-oriented method for automatically deploying an execution environment along with a job, including: presetting isolated execution environments at nodes of a high-performance computing system; logging in an isolated execution environment of a login node; carrying out development and debugging on the job and configuration on a job execution environment at the login node, and issuing a job running request to a job management system; assigning compute nodes from the nodes of the high-performance computing system to the job of the user by the job management system, automatically deploying an file system of the user synchronously to the assigned compute nodes along with the job when the job is loaded, and running the job of the user by the corresponding compute nodes; and feeding results back to the login node of the user after running the job is completed, then clearing file systems.

Description

CROSS-REFERENCE TO RELATED APPLICATION[0001]This application claims the priority benefit of China application serial no. 202011395015.4, filed on Dec. 3, 2020. The entirety of the above-mentioned patent application is hereby incorporated by reference herein and made a part of this specification.BACKGROUND OF THE INVENTION1. Technical Field[0002]The invention relates to the field of software of computer systems, and in particular, relates to a high-performance computing-oriented method for automatically deploying an execution environment along with a job.2. Description of Related Art[0003]In an existing high-performance computer system, physical nodes are divided into login nodes and compute nodes. After the users issue job requests at the login nodes, the high-performance computing system assigns the compute nodes through a job management system in response to these requests, thereby completing corresponding tasks. In this process, there are mainly the following modes at present.[00...

AI Technical Summary

Benefits of technology

[0015]To solve the technical problem, an object of the invention is to provide, in view of the technical problems existing in the prior art, a high-performance computing-oriented method for automatically deploying an execution environment along with a jog, which improves the job deployment efficiency in high-performance computing by a lightweight execution environment, reduces the burden of users to achieve almost negligible overhead, and reduces the burden of users in environment configuration.

Problems solved by technology

1. The user has a huge burden of deploying the job since the user needs to manually configure the environment in order to normally execute the job, and in the first method, the larger the number of the used compute nodes, the higher the burden of manual configuration; and

2. The original environment of the high-performance computing system is changed. A node that has been configured by one user would certainly affects its use by other users, leading to chaos of the configuration of system environment, and user privacy cannot be protected in such an environment.

The libraries and dependencies to be used by one job would be complicated.

1. Since the user encapsulates the execution environment of his / her own job by using a container, it is necessary to include the complete system environment required by this job in the content of the container, and the content must be manually maintained by the user, which brings a great burden to the user;

2. Besides encapsulating the execution environment of the job to generate the container image, the user also needs to manually deploy the container image to a compute node or a global shared filed system, and the job management system needs to be appointed to run this container image when the job is run by the job management system, both of which still bring a great burden to the user; and

3. The isolation technology used in the traditional container results in high performance overhead for running the job.

Images